docx-manipulation
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text and data to generate documents, which could allow malicious instructions within the input to influence agent behavior. * Ingestion points: User prompts for report generation, data tables, and contract placeholders. * Boundary markers: None defined to isolate or sanitize user-supplied content. * Capability inventory: Access to code_execution and file_operations tools. * Sanitization: No documented filtering or validation of user input before document insertion.
- [EXTERNAL_DOWNLOADS]: The skill specifies the installation of the python-docx package from public registries.
- [DYNAMIC_EXECUTION]: The skill generates and executes Python code at runtime to automate document formatting and creation tasks.
Audit Metadata